我正在尝试编写一个基本的双三次调整大小算法来调整24位RGB位图的大小。我对 the math 有一般性的了解,我正在使用Google代码中的this implementation作为指南。我这里没有使用任何外部库 - 我只是在尝试算法本身。位图表示为普通std::vector<unsigned char>
:
inline unsigned char getpixel(const std::vector<unsigned char>& in,
std::size_t src_width, std::size_t src_height, unsigned x, unsigned y, int channel)
{
if (x < src_width && y < src_height)
return in[(x * 3 * src_width) + (3 * y) + channel];
return 0;
}
std::vector<unsigned char> bicubicresize(const std::vector<unsigned char>& in,
std::size_t src_width, std::size_t src_height, std::size_t dest_width, std::size_t dest_height)
{
std::vector<unsigned char> out(dest_width * dest_height * 3);
const float tx = float(src_width) / dest_width;
const float ty = float(src_height) / dest_height;
const int channels = 3;
const std::size_t row_stride = dest_width * channels;
unsigned char C[5] = { 0 };
for (int i = 0; i < dest_height; ++i)
{
for (int j = 0; j < dest_width; ++j)
{
const int x = int(tx * j);
const int y = int(ty * i);
const float dx = tx * j - x;
const float dy = ty * i - y;
for (int k = 0; k < 3; ++k)
{
for (int jj = 0; jj < 4; ++jj)
{
const int z = y - 1 + jj;
unsigned char a0 = getpixel(in, src_width, src_height, z, x, k);
unsigned char d0 = getpixel(in, src_width, src_height, z, x - 1, k) - a0;
unsigned char d2 = getpixel(in, src_width, src_height, z, x + 1, k) - a0;
unsigned char d3 = getpixel(in, src_width, src_height, z, x + 2, k) - a0;
unsigned char a1 = -1.0 / 3 * d0 + d2 - 1.0 / 6 * d3;
unsigned char a2 = 1.0 / 2 * d0 + 1.0 / 2 * d2;
unsigned char a3 = -1.0 / 6 * d0 - 1.0 / 2 * d2 + 1.0 / 6 * d3;
C[jj] = a0 + a1 * dx + a2 * dx * dx + a3 * dx * dx * dx;
d0 = C[0] - C[1];
d2 = C[2] - C[1];
d3 = C[3] - C[1];
a0 = C[1];
a1 = -1.0 / 3 * d0 + d2 -1.0 / 6 * d3;
a2 = 1.0 / 2 * d0 + 1.0 / 2 * d2;
a3 = -1.0 / 6 * d0 - 1.0 / 2 * d2 + 1.0 / 6 * d3;
out[i * row_stride + j * channels + k] = a0 + a1 * dy + a2 * dy * dy + a3 * dy * dy * dy;
}
}
}
}
return out;
}
问题:当我使用此算法缩小图像时,它会起作用,但输出图像由于某种原因包含右侧的所有黑色像素,从而给出它被“裁剪”的外观。
示例:
INPUT IMAGE:
输出图像:
问题 :查看算法,我看不出为什么会这样。有人看到这里的缺陷吗?
答案 0 :(得分:12)
尽量不要交换宽度和高度。
for (int i = 0; i < dest_width; ++i)
{
for (int j = 0; j < dest_height; ++j)
答案 1 :(得分:2)
我建议不要使用此功能,因为它写得非常糟糕。你需要进行两次卷积:首先是X坐标,然后是Y.在这个函数中,所有这些卷积都在同一时间产生,导致工作非常慢。如果你看看jj循环体,你可以注意到身体的所有第二部分都是从“d0 = C [0] - C [1];”开始的。可以移到jj循环之外,因为只有这个循环的最后一次迭代才会对out []数组生效(所有先前的迭代结果都将被覆盖)。
答案 2 :(得分:0)
您应该在致电x
时切换z
和getpixel
,并在getpixel
中使用以下内容对数组编制索引:
[(y * 3 * src_width) + (3 * x) + channel]
答案 3 :(得分:0)
在getpixel(in, src_width, src_height, z, x, k)
:
z mean horizontal offset
x mean vertical offset
所以只需要修补getpixel
函数,下面是修补后的代码:
inline unsigned char getpixel(const std::vector<unsigned char>& in,
std::size_t src_width, std::size_t src_height, unsigned y, unsigned x, int channel)
{
if (x < src_width && y < src_height)
return in[(y * 3 * src_width) + (3 * x) + channel];
return 0;
}
std::vector<unsigned char> bicubicresize(const std::vector<unsigned char>& in,
std::size_t src_width, std::size_t src_height, std::size_t dest_width, std::size_t dest_height)
{
std::vector<unsigned char> out(dest_width * dest_height * 3);
const float tx = float(src_width) / dest_width;
const float ty = float(src_height) / dest_height;
const int channels = 3;
const std::size_t row_stride = dest_width * channels;
unsigned char C[5] = { 0 };
for (int i = 0; i < dest_height; ++i)
{
for (int j = 0; j < dest_width; ++j)
{
const int x = int(tx * j);
const int y = int(ty * i);
const float dx = tx * j - x;
const float dy = ty * i - y;
for (int k = 0; k < 3; ++k)
{
for (int jj = 0; jj < 4; ++jj)
{
const int z = y - 1 + jj;
unsigned char a0 = getpixel(in, src_width, src_height, z, x, k);
unsigned char d0 = getpixel(in, src_width, src_height, z, x - 1, k) - a0;
unsigned char d2 = getpixel(in, src_width, src_height, z, x + 1, k) - a0;
unsigned char d3 = getpixel(in, src_width, src_height, z, x + 2, k) - a0;
unsigned char a1 = -1.0 / 3 * d0 + d2 - 1.0 / 6 * d3;
unsigned char a2 = 1.0 / 2 * d0 + 1.0 / 2 * d2;
unsigned char a3 = -1.0 / 6 * d0 - 1.0 / 2 * d2 + 1.0 / 6 * d3;
C[jj] = a0 + a1 * dx + a2 * dx * dx + a3 * dx * dx * dx;
d0 = C[0] - C[1];
d2 = C[2] - C[1];
d3 = C[3] - C[1];
a0 = C[1];
a1 = -1.0 / 3 * d0 + d2 -1.0 / 6 * d3;
a2 = 1.0 / 2 * d0 + 1.0 / 2 * d2;
a3 = -1.0 / 6 * d0 - 1.0 / 2 * d2 + 1.0 / 6 * d3;
out[i * row_stride + j * channels + k] = a0 + a1 * dy + a2 * dy * dy + a3 * dy * dy * dy;
}
}
}
}
return out;
}